R Notebook

This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Ctrl+Shift+Enter.

source("./tianfengRwrappers.R")

# plan("multiprocess",workers = 8)

#冠状动脉

human_coronary_countmatrix <- read.csv("GSE131778_human_coronary_scRNAseq.txt", sep = "\t")
func <- function(s) {
  paste0(strsplit(s, ".", fixed = T)[[1]][2], "_", strsplit(s, ".", fixed = T)[[1]][1])
}
colnames(human_coronary_countmatrix) <- lapply(colnames(human_coronary_countmatrix), func) # 拆分样本

颈动脉斑块 CA dataset1

# 批量读取计数矩阵
# 需要把行名的gene删掉，用vscode修改
count_mats <- list.files("./CA_GSE155512")
count_mats <- count_mats[count_mats != "sampleinfo.txt"]
allList <- lapply(count_mats, function(folder) {
  CreateSeuratObject(
    counts = read.csv(paste0("./CA_GSE155512/", folder), sep = "\t"),
    project = folder, min.cells = 10, min.features = 300
  )
})
# 合并seurat对象
CA_dataset1 <- merge(allList[[1]],
  y = allList[-1], add.cell.ids = count_mats,
  project = "CA_dataset1"
)
rm(allList)

CA_dataset1 <- PercentageFeatureSet(CA_dataset1, pattern = "^MT-", col.name = "percent.mt") %>%
    subset(subset = nFeature_RNA > 600 & nFeature_RNA < 6000 & nCount_RNA > 1000 &  nCount_RNA < 30000) %>%
    SCTransform(vars.to.regress = "percent.mt", verbose = F) %>% 
    RunPCA() %>% FindNeighbors(dims = 1:20) %>% 
    RunUMAP(dims = 1:20) %>% 
    FindClusters(resolution = 0.1)

颈动脉斑块 CA dataset2

CA_dataset2 <- CreateSeuratObject(Read10X("./CA_GSE159677/"), names.field = 2, names.delim = "-",
                                     project = "CA_dataset2", min.cells = 10, min.features = 300) %>% 
    PercentageFeatureSet(pattern = "^MT-", col.name = "percent.mt") %>%
    subset(subset = nFeature_RNA > 600 & nFeature_RNA < 6000 & nCount_RNA > 1000 &  nCount_RNA < 30000) %>%
    SCTransform(vars.to.regress = "percent.mt", verbose = F) %>% 
    RunPCA() %>% FindNeighbors(dims = 1:20) %>% 
    RunUMAP(dims = 1:20) %>% 
    FindClusters(resolution = 0.1)

添加metadata samples存储完整信息，conditions按区域分，groups按病例分

Idents(human_coronary) <- human_coronary$orig.ident
Idents(human_coronary) <- c("1","1","2","2","3","3","4","4")
human_coronary$samples <- Idents(human_coronary)
Idents(human_coronary) <- human_coronary$seurat_clusters

Idents(CA_dataset2) <- CA_dataset2$orig.ident
CA_dataset2 <- RenameIdents(CA_dataset2,'1' = 'AC_1','2' = 'PA_1','3' = 'AC_2','4' = 'PA_2','5' = 'AC_3','6' = 'PA_3')
UMAPPlot(CA_dataset2)

CA_dataset2$sample <- Idents(CA_dataset2)
CA_dataset2 <- RenameIdents(CA_dataset2,'AC_1' = 'AC','PA_1' = 'PA','AC_2'= 'AC','PA_2'= 'PA','AC_3'= 'AC','PA_3'= 'PA')
CA_dataset2$conditions <- Idents(CA_dataset2)
Idents(CA_dataset2) <- CA_dataset2$orig.ident
CA_dataset2 <- RenameIdents(CA_dataset2, '1' = 'sp_1','2' = 'sp_1','3' = 'sp_2','4' = 'sp_2','5' = 'sp_3','6' = 'sp_3')
CA_dataset2$groups <- Idents(CA_dataset2)
Idents(CA_dataset2) <- CA_dataset2$seurat_clusters

保存结果

saveRDS(human_coronary,"human_coronary.rds")
saveRDS(CA_dataset1,"CA_dataset1.rds")
saveRDS(CA_dataset2,"CA_dataset2.rds") #已经经过分组处理了

---

读取结果

human_coronary <- readRDS("human_coronary.rds")
CA_dataset1 <- readRDS("CA_dataset1.rds")
CA_dataset2 <- readRDS("CA_dataset2.rds") #已经经过分组处理了

修改分群

基质细胞分类

ECs亚群分析 整合

整合算法可能出现负值，运行SCENIC时舍弃了这些异常值

# 提取内皮细胞亚群
ECs_list <- list(subset(CA_dataset1, idents = "Endothelial"), subset(human_coronary, idents = "Endothelial"))

ECs_list <- lapply(X = ECs_list, FUN = function(x) {
  x <- NormalizeData(x)
  x <- FindVariableFeatures(x, selection.method = "vst", nfeatures = 2000)
})
# 需要分析的差异基因
int_features <- SelectIntegrationFeatures(object.list = ECs_list)
# 选择合并的anchor特征
int_anchors <- FindIntegrationAnchors(object.list = ECs_list, anchor.features = int_features)

# 根据anchor合并
ECs_combined <- IntegrateData(anchorset = int_anchors)

DefaultAssay(ECs_combined) <- "integrated"
rm("ECs_list", "int_features", "int_anchors")

multi_featureplot(c("TNFRSF11B","ACTA2","CNN1","LUM"),human_coronary)

multi_featureplot(c("TNFRSF11B","ACTA2","CNN1","LUM"),CA_dataset1)

multi_featureplot(c("TNFRSF11B","ACTA2","CNN1","LUM"),CA_dataset2)